data import
- Load data into the table (Load)
usage:
hive>load data [local] inpath '/opt/module/datas/student.txt' [overwrite] into table student [partition (partcol1=val1,…)];
(1) load data: means to load data
(2) local : Indicates loading data from local to hive table; otherwise, loading data from HDFS to hive table
(3) inpath: Indicates the path to load data
(4) into table: Indicates which table to load into
(5) student: Indicates a specific table
( 6) overwrite: means overwriting the existing data in the table, otherwise means appending
(7) partition: means uploading to the specified partition
create a table hive (default)> create table student(id string, name string) row format delimited fields terminated by '\t'; Load local files to hive hive (default)> load data local inpath '/opt/module/datas/student.txt' into table default.student; Load HDFS file into hive Upload files to HDFS
hive (default)> dfs -put /opt/module/datas/student.txt /user/lzl/hive;
load data on HDFS
hive (default)>load data inpath '/user/lzl/hive/student .txt' into table default.student;Loading data overwrites existing data in the table Upload files to HDFS
hive (default)> dfs -put /opt/module/datas/student.txt /user/lzl/hive;
load data to cover the existing data in the table
hive (default)>load data inpath '/user/ lzl/hive/student.txt' overwrite into table default.student; - Insert data into a table through a query statement (Insert)
Create a partition table hive (default)> create table student(id string, name string) partitioned by (month string) row format delimited fields terminated by '\t'; basic insert data hive (default)> insert into table student partition(month='201805') values('1004','wangwu'); Basic schema insertion (query results based on a single table) hive (default)> insert overwrite table student partition(month='201805')
select id, name from student where month='201806';多插入模式(根据多张表查询结果) hive (default)> from student
insert overwrite table student partition(month='201805')
select id, name where month='201809'
insert overwrite table student partition(month='201806')
select id, name where month='201809'; - 查询语句中创建表并加载数据(As Select)
详情查看https://blog.csdn.net/liangzelei/article/details/80147866中的创建表
根据查询结果创建表(查询的结果会添加到新创建的表中)
create table if not exists student3
as select id, name from student; - 创建表时通过Location指定加载数据路径
创建表,并指定在hdfs上的位置 hive (default)> create table if not exists student5(id int, name string)
row format delimited fields terminated by '\t'
location '/user/hive/warehouse/student5';上传数据到hdfs上 hive (default)> dfs -put /opt/module/datas/student.txt /user/hive/warehouse/student5; 查询数据 hive (default)> select * from student5; - Import数据到指定Hive表中
先用export导出后,再将数据导入
(注意支持出export导出的文件)hive (default)> import table student2 partition(month='201709') from
'/user/hive/warehouse/export/student';
数据导出
- Insert导出
将查询的结果导出到本地 hive (default)> insert overwrite local directory '/opt/module/datas/export/student'
select * from student;将查询的结果格式化导出到本地 hive (default)> insert overwrite local directory '/opt/module/datas/export/student1'
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' COLLECTION ITEMS TERMINATED BY '\n'
select * from student;将查询的结果导出到HDFS上(没有local) hive (default)> insert overwrite directory '/user/atguigu/hive/warehouse/student2'
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' COLLECTION ITEMS TERMINATED BY '\n'
select * from student; - Hadoop命令导出到本地
hive (default)> dfs -get /user/hive/warehouse/student/month=201805/000000_0 /opt/module/datas/export/student3.txt; - Hive Shell 命令导出
$ bin/hive -e 'select * from default.student;' > /opt/module/datas/export/student4.txt; - Export导出到HDFS上
hive (default)> export table default.student to '/user/hive/warehouse/export/student'; - Sqoop导出
未完待续......
清除表中数据
hive (default)> truncate table student;
注意:Truncate只能删除管理表,不能删除外部表中数据